Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 2 papers
Filter5

Model risks

Deception and scheming2Dangerous agent actions8

Defense type

Instruction–data separation1Permissions and approval1Monitoring and auditing5

System type

coding agent2Embodied systems and robotics0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Model risks：Deception and schemingDefense type：Instruction–data separationDefense type：Permissions and approvalSystem type：coding agentSystem type：Embodied systems and roboticsClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2609.36170

    Assay：用内容寻址证据图约束 AI 编码智能体的声明失效

    提出 Assay，用依赖锥哈希绑定代码断言并在合并门禁拦截失效声明

    arXiv
    2609.36170
    Published
    Layer
    Application layer
    Setting
    coding agent
    AbstractAssay 提供随依赖内容失效的证据管理。

    Assay 是一套面向 AI 辅助软件交付的内容寻址证据系统，关注代码改变后，测试通过、无秘密或行为保持等断言还能否用于批准合并。

    Paper analysisRead analysis
  2. DefensesarXiv 2609.19587

    红队测试 Auto Mode：用注入与多上下文攻击绕过编码 Agent 阻断监控器

    提出 Auto Mode ++，加固编码 Agent 阻断监视器

    arXiv
    2609.19587
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Opus 5, Opus 4.8, Opus 4.7 and others8

    Abstract系统评估生产阻断监视器在面对持续恶意智能体时的表现，提出加固防御并指明多上下文防御挑战。

    Paper analysisRead analysis
You have reached the end